A novel scheme for speaker recognition using a phonetically-aware deep neural network

YUN LEI; NICOLAS SCHEFFER; LUCIANA FERRER; MITCH MCLAREN

Florencia

Congreso; IEEE Conference on Acoustics, Speech, and Signal Processing (ICASSP); 2014

IEEE

We propose a novel framework for speaker recognition in which extraction of sufficient statistics for the state-of-the-art i-vector model is driven by a deep neural network (DNN) trained for auto- matic speech recognition (ASR). Specifically, the DNN replaces the standard Gaussian mixture model (GMM) to produce frame align- ments. The use of an ASR-DNN system in the speaker recognition pipeline is attractive as it integrates the information from speech content directly into the statistics, allowing the standard backends to remain unchanged. Improvement from the proposed framework compared to a state-of-the-art system are of 30% relative at the equal error rate when evaluated on the telephone conditions from the 2012 NIST speaker recognition evaluation (SRE). The proposed framework is a successful way to efficiently leverage transcribed data for speaker recognition, thus opening up a wide spectrum of research directions.